NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of NeurIPS 2026
Abstract
The safe for work edition of acceptodds: the submissions, without the markets. Search them, browse them on a map laid out by what they are about, follow the ones you care about, keep reading lists with your group, and get recommendations from what you read. There are no odds, no bets and no reputation here. acceptodds is not affiliated with any organisation or institution. acceptodds is an open source project, open to contributions, at github.com/PotentialHedge/acceptodds-sfw.1 Follow for updates on X.
[PDF]Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent EnsemblesDONG LAO, Yuxiang Zhang, Haniyeh E Oskouie et al.3.67
[PDF]Rethinking Personalized Generation: Test-time Alignment via Factorized Ranking ModelsQiyao Ma, Junshan Zhang, Zhe Zhao3.67
[abs]ReGen: Agentic Video World Modeling with Synergized Reasoning and GenerationChenguo Lin, Yu Tang, Weiqiao Zheng et al.3.67
[abs]Salvation Lies Within: Proactive Prefix Re-forming for LLM-based TaggingSHULAN WANG, YingJie Zhu, Yuting Yan et al.3.67
[PDF]Guiding Visual Autoregressive Models through Spectrum WeakeningChaoyang Wang, Tianmeng Yang, Yunhai Tong3.67
[PDF]Spectral Feedback for Test-Time Alignment of Protein Diffusion ModelsShai Dickman, Mert Cemri, Landon Butler et al.3.67
[abs]SceneShifter: Training-free Multi-Scene Temporal Control for Audio-driven Human AnimationJianzhi Long, Rong-Cheng Tu, Hao Guan et al.3.67
[PDF]When Policies Cannot Be Retrained: A Unified Closed-Form View of Post-Training Steering in Offline Reinforcement LearningElias Hossain, Mohammad J Basher, Ivan Garibay et al.3.67
[PDF]FedVSSAM: Mitigating Flatness Incompatibility in Sharpness-Aware Federated LearningBingnan Xiao, Yuan Gao, Bingcong Li et al.3.67
[PDF]AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented GenerationZhengren Wang, Dongsheng Ma, Huaping Zhong et al.3.67
[PDF]CofactVLA: Deconfounding Vision-Language-Action Models via Counterfactual InterventionYan Zhang, Yinan Wu, Haoran Duan et al.3.67
[abs]Learning a Trajectory-Geometric Condition from Reasoning for VLA PlanningYuguang Yang, Zhewen Tan, Canyu Chen et al.3.67
[abs]Projection Learning: A Principled Way to Overcome Memorization in Distribution LearningLin Chen, Dejan Slepcev3.67
[abs]Stability and Diversity of Networked Self-Consuming Generative EcosystemsXiukun Wei, Yang Zhang, Xueru Zhang3.67
[PDF]EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic ExperienceTaofeng Xue, Chong Peng, Mianqiu Huang et al.3.67
[abs]There are Levels to It: Red Teaming LLMs with Hierarchical Reinforcement LearningRoman Belaire, Arunesh Sinha, Pradeep Varakantham3.67
[PDF]Rank Is Not Capacity: Spectral Occupancy for Latent Graph ModelsNikolaos Nakis, Panagiotis Promponas, Konstantinos Tsirkas et al.3.67
[abs]Strong Post-Training from Permissive, Reasoning-Dominant, Web-Scale PretrainingHarsh Raj, Ali Elganzory, Marianna Nezhurina et al.3.67
[PDF]Partition Tree: Conditional Density Estimation over General Outcome SpacesFelipe Lourenco Angelim Vieira, Alessandro Leite3.67
[PDF]Cost Efficient Fairness Audit Under Partial FeedbackNirjhar Das, mohit sharma, Praharsh Nanavati et al.3.67
[abs]Plug-and-Play ADMM for Inverse Problems with Flow Matching DenoiserDibyanshu Kumar, Magda Gregorova3.67
[PDF]FrED: External Data Influence Estimation via Domain Knowledge Graph GroundingTheodoros Aivalis, Iraklis A Klampanos, Antonis Troumpoukis et al.3.67
[PDF]VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video DiffusionHidir Yesiltepe, Jiazhen Hu, Tuna Han Salih Meral et al.3.67
[abs]WaveSem: Frequency-Adaptive Tokenization for Disentangling Semantics and Noise in GenomicsShou Z Chen, Bing He, Zhenchao Tang et al.3.67
[abs]Imperfect Influence, Reliable Rankings: A Theory of TRAK for Data AttributionHan Tong, Shubhangi Ghosh, Haolin Zou et al.3.67
[abs]XTraj: A Coarse-to-Fine Autoregressive Framework for Transferable Trajectory Generationwang chao, ZHIQUAN LAI, Xinwei Fang et al.3.67
[abs]One-Layer Transformers Provably Learn In-Context K-Nearest Neighbor Prediction with Chain-of-ThoughtLyumin Wu, Yuan Cao3.67
[abs]Q-CoMove: Differentiable Quantum Circuit Priors for Coordinated Motion in Multi-Component Embodied SystemsKe Shi, Fanqi Kong, Yuchen Wang et al.3.67
[PDF]Deep Reasoning in General Purpose Agents via Structured Meta-CognitionDean Light, Michael Theologitis, Kshitish Ghate et al.3.67
[PDF]From Persistence to Survival: Hypothesis Testing, Effect Sizes and Vectorisation for Topological FeaturesJuliette Murris, Bernadette J Stolz, Karsten Borgwardt3.67
[PDF]A Unified Framework for Adversary-Aware Differential Privacy BoundsMarika Swanberg, Meenatchi Sundaram Muthu Selva Annamalai, Jamie Hayes et al.3.67
[abs]-Aware Conditional Distribution Transport for Vehicle Trajectory GenerationDi Wen, Zhaocheng He, Shuhui Wang3.67
[PDF]Take It or Leave It: Intent-Controlled Partial Optimal TransportParth TRIPATHI, bertrand chapron, Fabrice collard et al.3.67
[abs]Semantic-Bridge Federated Learning: Bridging CLIP Semantics for Heterogeneous FLLeixuhai Xu, Xiangtao Zhang, Hailong Yan et al.3.67
[PDF]Conditional Optimal Bridge for Riemannian Activation SteeringSeyed Arshan Dalili, Ajay Narayanan Sridhar, Vijaykrishnan Narayanan et al.3.67
[abs]ASQ: Agent-guided Semantic-aware Quantization for Large Language ModelsSeungdong Yoa, Ye Seul Sim, Suhee Yoon et al.3.67
[PDF]When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond HorizonHuaqing Zhang, Jingchu Gai, Juno Kim et al.3.67
[abs]Forgery Evidence Peaks Mid-Stack: Forensic Evidence Relay for Multimodal Forgery DetectionYingxin Lai, xinyuan Wang, Yufei Liu et al.3.67
[abs]Random Attention Pattern Learning Enables Emergent CapabilitiesVatsal Baherwani, Charlie Chen, Shikai Qiu et al.3.67
[abs]Policy-Level Exploration for Coordinated Multi-Agent Reinforcement LearningYucong Zhang, Chao Yu3.67
[abs]Random-Effects Centroids for Domain GeneralizationJinyong Jeong, Hyungu Kahng, Seoung Bum Kim3.67
[PDF]LLM Judge Validation Under Sparse Overlap: From Inference to DesignJunxuan Li, Arko Mukherjee, Soumyabrata Pal3.67
[abs]MHWA: Multi-timescale Hierarchical World-Action ModelPengcheng Pan, Guoqing Ma, Yuhan Zhang et al.3.67
[abs]RILA: A Radar-Native Structured Interface from Sparse mmWave Point Clouds to Large Language ModelsShenglei Li, Tomoji Kishi3.67
[PDF]PEEK: Context Map as an Orientation Cache for Long-Context LLM AgentsZhuohan Gu, Qizheng Zhang, Omar Khattab et al.3.67
[abs]PRISM: Human Point Cloud Reconstruction via Skeleton-Guided Diffusion from MmWave RadarJiacheng Huang, Long Tian, Yuan Liu et al.3.67
1 If this project is interesting to you, reach out at [email protected].